ROC curve
Let's now create an ROC curve for our random forest classifier. The first step is to calculate the predicted probabilities output by the classifier for each label using its .predict_proba()
method. Then, you can use the roc_curve
function from sklearn.metrics
to compute the false positive rate and true positive rate, which you can then plot using matplotlib
.
A RandomForestClassifier
with a training set size of 70% has been fit to the data and is available in your workspace as clf
.
This exercise is part of the course
Marketing Analytics: Predicting Customer Churn in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Generate the probabilities
y_pred_prob = ____.____(____)[:, 1]